[Insight-users] Sign missing in SSD derivative in Insight into images

Luis Ibanez luis.ibanez at kitware.com
Thu May 26 12:10:07 EDT 2011


Hi Brecht,

Thanks for pointing this out.

I agree with your correction.

The derivative should be getting the "-" sign from "M(T(xi,p))",
from inside of the [F-M] term.


    Thanks


          Luis


--------------------------------
On Wed, May 25, 2011 at 9:34 AM, Brecht Heyde
<Brecht.Heyde at med.kuleuven.be> wrote:
> Hi Luis, hi Lydia,
>
> In your contribution in "Insight Into Images", I think there is a negative sign missing in formula 10.103, p 280 in "Insight into Images", showing the SSD derivative to the transform parameters.
> I think it should be -2/N sum( [F-M]*dM/dp).
> I'm not sure if this has been reported already. I have the 2004 book version.
>
> The code itself is doing it correctly: line 202 and 224 of itkMeanSquaresImageToImageMetric.txx: 2/N sum ([M-F]*dM/dp ). Notice that F and M have switched positions.
>
> Best regards,
> Brecht Heyde
> _____________________________________
> Powered by www.kitware.com
>
> Visit other Kitware open-source projects at
> http://www.kitware.com/opensource/opensource.html
>
> Kitware offers ITK Training Courses, for more information visit:
> http://www.kitware.com/products/protraining.html
>
> Please keep messages on-topic and check the ITK FAQ at:
> http://www.itk.org/Wiki/ITK_FAQ
>
> Follow this link to subscribe/unsubscribe:
> http://www.itk.org/mailman/listinfo/insight-users
>


More information about the Insight-users mailing list